Generative Media Infrastructure Engineer
Async multi-provider AI content generation framework for music, video, and images with plugin providers, style presets, CLI workflows, job tracking, duplicate detection, and cost controls.
"Unified music, image, and video generation into a provider-agnostic pipeline with persistent job management."

Generative media APIs have inconsistent capabilities, long-running jobs, duplicate-cost risks, provider lock-in, and messy post-processing paths from source material to final output.
Built a typed plugin architecture for Google, AIMLAPI, and Kling providers, plus style presets, Archive.org source discovery, SQLite job tracking, async status sync, FFmpeg media merge, and export workflows.
TRP1 AI Artist orchestrates music, image, and video generation across multiple providers. It can search source material, run parallel generation jobs, merge media locally, and prepare outputs for YouTube or S3.
Case studies in similar engineering domains.
Fork and evaluation workspace for DAB, a realistic enterprise data-agent benchmark spanning multi-database integration, messy joins, unstructured text transformation, and domain knowledge.
Sales-domain benchmark and trained critic layer for Tenacious-style B2B outreach, with contamination-aware task generation, deterministic scoring checks, preference data, and a small LoRA judge.
Spec-driven autonomous influencer network foundation using FastRender Swarm architecture, MCP-only external IO, Planner/Worker/Judge task DAGs, HITL review, multi-tenancy, and budget governance.